Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/docker.yml
#	ci/run.sh
#	docs/build.md
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	src/llama-vocab.cpp
#	tests/test-chat.cpp
#	tests/test-jinja.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/server/README.md
This commit is contained in:
Concedo
2026-04-04 14:27:23 +08:00
parent 235ec9a1b9 d006858316
commit 2e4f94822e
15 changed files with 464 additions and 149 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+8
View File
@@ -1314,6 +1314,14 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.kv_unified = value;
}
).set_env("LLAMA_ARG_KV_UNIFIED").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_PERPLEXITY, LLAMA_EXAMPLE_BATCHED, LLAMA_EXAMPLE_BENCH, LLAMA_EXAMPLE_PARALLEL}));
add_opt(common_arg(
{"--clear-idle"},
{"--no-clear-idle"},
"save and clear idle slots on new task (default: enabled, requires unified KV and cache-ram)",
[](common_params & params, bool value) {
params.clear_idle = value;
}
).set_env("LLAMA_ARG_CLEAR_IDLE").set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--context-shift"},
{"--no-context-shift"},